© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 28776
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "st" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    243
    +0.10
    0.5%
    128
    +0.08
    0.4%
    450
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    243
    +0.10
    0.02
    128
    +0.08
    0.02
    232
    +0.08
    0.02
    Negative Logits
     Luxembourg
    -0.72
     Principles
    -0.63
     Theft
    -0.61
     chronological
    -0.59
     Union
    -0.57
     Limit
    -0.56
     ministerial
    -0.56
     Moz
    -0.56
     compulsion
    -0.56
     touch
    -0.55
    POSITIVE LOGITS
    onew
    1.25
    umbles
    1.12
    upe
    1.05
    inky
    1.04
    ashed
    1.01
    roller
    0.98
    onel
    0.98
    oned
    0.98
    aved
    0.98
    itched
    0.97
    Activations Density 0.061%

    No Known Activations